Comparision Of Adversarial And Non-Adversarial LSTM Music Generative Models

TL;DR

This paper compares adversarial and non-adversarial training methods for LSTM-based music generation, showing that adversarial training yields more aesthetically pleasing compositions according to human evaluations.

Contribution

It introduces a comparative analysis of adversarial versus non-adversarial training for RNN music models using MIDI data, highlighting the benefits of adversarial approaches.

Findings

Adversarial training produces more aesthetically pleasing music.

Human listeners prefer adversarially generated samples.

Adversarial models increase note variety in generated music.

Abstract

Algorithmic music composition is a way of composing musical pieces with minimal to no human intervention. While recurrent neural networks are traditionally applied to many sequence-to-sequence prediction tasks, including successful implementations of music composition, their standard supervised learning approach based on input-to-output mapping leads to a lack of note variety. These models can therefore be seen as potentially unsuitable for tasks such as music generation. Generative adversarial networks learn the generative distribution of data and lead to varied samples. This work implements and compares adversarial and non-adversarial training of recurrent neural network music composers on MIDI data. The resulting music samples are evaluated by human listeners, their preferences recorded. The evaluation indicates that adversarial training produces more aesthetically pleasing music.